Augmentative Topology Agents For Open-Ended Learning

2022-10-20 · Muhammad Umair Nasir, Michael Beukman, Steven James, Christopher Wesley Cleghorn

In this work, we tackle the problem of open-ended learning by introducing a method that simultaneously evolves agents and increasingly challenging environments. Unlike previous open-ended approaches that optimize agents using a fixed neural network topology, we hypothesize that generalization can be improved by allowing agents' controllers to become more complex as they encounter more difficult environments. Our method, Augmentative Topology EPOET (ATEP), extends the Enhanced Paired Open-Ended Trailblazer (EPOET) algorithm by allowing agents to evolve their own neural network structures over time, adding complexity and capacity as necessary. Empirical results demonstrate that ATEP results in general agents capable of solving more environments than a fixed-topology baseline. We also investigate mechanisms for transferring agents between environments and find that a species-based approach further improves the performance and generalization of agents.

📄 PDF Abstract BibTeX arXiv:2210.11442

Code (2)

umair-nasir14/atep 공식 구현

umair-nasir14/atep_llr 공식 구현

Dialogue Act Classification for Augmentative and Alternative Communication

2021-08-01 · ACL (NLP4PosImpact) 2021 8 · E. Margaret Perkoff

Augmentative and Alternative Communication (AAC) devices and applications are intended to make it easier for individuals with complex communication needs to participate in conversations. However, these devices have low a…

Classification Dialogue Act Classification Recommendation Systems

Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents

2024-07-05 · Sam Earle, Julian Togelius

We introduce Autoverse, an evolvable, domain-specific language for single-player 2D grid-based games, and demonstrate its use as a scalable training ground for Open-Ended Learning (OEL) algorithms. Autoverse uses cellula…

GPU Imitation Learning Reinforcement Learning (RL)Sokoban

Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations

2026-08-01 · Xinshun Feng, Ziqi Miao, Lijun Li, Jing Shao arxiv

Large language model (LLM) agents are increasingly deployed in scientific research, where reliability is critical and the underlying knowledge is densely interconnected. In such settings, hallucinations are particularly …

Code Generation

Rewardless Open-Ended Learning (ROEL)

2021-09-29 · Alexander Quessy, Thomas Stuart Richardson

Open-ended learning algorithms aim to automatically generate challenges and solutions to an unending sequence of learning opportunities. In Reinforcement Learning (RL) recent approaches to open-ended learning, such as Pa…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Unsupervised Reinforcement Learning

OpenSage: Self-programming Agent Generation Engine

2026-02-18 · Hongwei Li, Zhun Wang, Qinrun Dai, Yuzhou Nie 외 arxiv

Agent development kits (ADKs) provide effective platforms and tooling for constructing agents, and their designs are critical to the constructed agents' performance, especially the functionality for agent topology, tools…